triadic-voice-v2

name	triadic-voice-v2
description	HFR v2 generator. Same in-session Russell+Feynman+Hoskinson fusion as triadic-voice, but register-routed, chassis-varied, and profile-target-driven, with an anti-copy self-check. Use when generating v2 passages for the HFR comparison. The running model is the generator; no API key.
license	MIT
metadata	{"author":"charles-hoskinson","version":"0.1.0","category":"writing"}

triadic-voice-v2

The v2 HFR generator. Same fused Russell+Feynman+Hoskinson voice and same in-session doctrine as triadic-voice (the running model writes; no API key), but generation is register-routed, chassis-varied, profile-target-driven, and anti-copy-checked. The v1 triadic-voice skill is unchanged and remains the comparison control.

How to generate (in-session)

1. Build the brief. Call build_generation_brief(topic, rotation) (from skill_api). It returns the register, a chassis (beat plan), numeric targets + an injectable targets_prompt, and an exemplar_query. rotation increments per passage so the chassis varies across a batch.
2. Ground in the real voice. Read 6–10 Hoskinson corpus entries matching the exemplar_query (register + rhetorical move) and the fusion guide . Study cadence; never copy wording.